Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    predicate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uces
    -0.08
    _comm
    -0.07
    经验
    -0.07
    Infos
    -0.07
     assist
    -0.06
    댤
    -0.06
    (filter
    -0.06
    反馈
    -0.06
     operator
    -0.06
     anticipating
    -0.06
    POSITIVE LOGITS
    .readFile
    0.07
    getField
    0.07
     sheriff
    0.07
     structural
    0.07
    שן
    0.07
    🚗
    0.07
     uu
    0.07
    UF
    0.06
    ól
    0.06
    قلب
    0.06
    Act Density 0.004%

    No Known Activations